import numpy as np
import pandas as pd

from IPython.display import display, display_html , HTML

import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.decomposition import PCA

from sklearn.model_selection import train_test_split

from sklearn.metrics import f1_score, accuracy_score, confusion_matrix, classification_report, roc_curve
from sklearn.model_selection import learning_curve, cross_val_score, GridSearchCV
from sklearn.model_selection import train_test_split

from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
from sklearn.svm import SVC
from sklearn.pipeline import make_pipeline
from sklearn.neighbors import KNeighborsClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import RobustScaler,StandardScaler,MinMaxScaler

import warnings
warnings.filterwarnings('ignore')

characteristics = pd.read_csv('../input/2019-database-of-road-traffic-injuries/caracteristiques-2019.csv')
characteristics.name = 'characteristics'
places = pd.read_csv('../input/2019-database-of-road-traffic-injuries/lieux-2019.csv')
places.name = 'places'
drivers = pd.read_csv('../input/2019-database-of-road-traffic-injuries/usagers-2019.csv')
drivers.name = 'drivers'
vehicles = pd.read_csv('../input/2019-database-of-road-traffic-injuries/vehicules-2019.csv')
vehicles.name = 'vehicles'

datasets = [characteristics,places,vehicles,drivers]

characteristics = characteristics.set_index('Num_Acc')
places = places.set_index('Num_Acc')
vehicles = vehicles.set_index('id_vehicule')
drivers = drivers.set_index('id_vehicule')

pd.set_option('display.max_row',max(characteristics.shape[0],places.shape[0],drivers.shape[0],vehicles.shape[0]))
pd.set_option('display.max_column',max(characteristics.shape[1],places.shape[1],drivers.shape[1],vehicles.shape[1]))

for df in datasets:
    print ("The dataset",df.name,"has",df.shape[0],"rows and",df.shape[1],"columns")

The dataset characteristics has 58840 rows and 15 columns
The dataset places has 58840 rows and 18 columns
The dataset vehicles has 100710 rows and 11 columns
The dataset drivers has 132977 rows and 15 columns

display(HTML('<h1>characteristics</h1>'))
display(characteristics.head())
display(HTML('<h1>vehicles</h1>'))
display(vehicles.head())
display(HTML('<h1>drivers</h1>'))
display(drivers.head())
display(HTML('<h1>places</h1>'))
display(places.head())

display(HTML('<h1><center>Missing values of the different tables (%)</center></h1>'))

a = pd.DataFrame(np.transpose(np.array((characteristics.columns,round(characteristics.isna().sum()/characteristics.shape[0]*100,2)),dtype=object,)),columns=['features','missing_rate'])
b = pd.DataFrame(np.transpose(np.array((vehicles.columns,round(vehicles.isna().sum()/vehicles.shape[0]*100,2)),dtype=object,)),columns=['features','missing_rate'])
c = pd.DataFrame(np.transpose(np.array((places.columns,round(places.isna().sum()/places.shape[0]*100,2)),dtype=object,)),columns=['features','missing_rate'])
d = pd.DataFrame(np.transpose(np.array((drivers.columns,round(drivers.isna().sum()/drivers.shape[0]*100,2)),dtype=object,)),columns=['features','missing_rate'])

def highlight_greaterthan(x):
    if x.missing_rate > 80:
        return ['background-color: #FFCECE']*2
    if x.missing_rate > 40:
        return ['background-color: #FFE9CE']*2
    if x.missing_rate > 5:
        return ['background-color: #FFFECE']*2
    else:
        return ['background-color: #CEFFFC']*2
    
a = a.style.apply(highlight_greaterthan, axis=1).set_table_styles([{
    'selector': 'caption',
    'props': [
        ('color', '#585858'),
        ('font-size', '30px')
    ]
}])
b = b.style.apply(highlight_greaterthan, axis=1).set_table_styles([{
    'selector': 'caption',
    'props': [
        ('color', '#585858'),
        ('font-size', '30px')
    ]
}])
c = c.style.apply(highlight_greaterthan, axis=1).set_table_styles([{
    'selector': 'caption',
    'props': [
        ('color', '#585858'),
        ('font-size', '30px')
    ]
}])
d = d.style.apply(highlight_greaterthan, axis=1).set_table_styles([{
    'selector': 'caption',
    'props': [
        ('color', '#585858'),
        ('font-size', '30px')
    ]
}])

a_styler = a.set_table_attributes("style='display:inline'").set_caption('characteristics')
b_styler = b.set_table_attributes("style='display:inline'").set_caption('vehicles')
c_styler = c.set_table_attributes("style='display:inline'").set_caption('places')
d_styler = d.set_table_attributes("style='display:inline'").set_caption('drivers')

space = "\xa0" * 50
display_html(a_styler._repr_html_() + space + b_styler._repr_html_() + space + c_styler._repr_html_() + space + d_styler._repr_html_(), raw=True)

display(HTML('<h3><i>The values highlighted are the ones above a certain threshold of missing values</i></h3>'))
display(HTML('<h3><i>We will get rid of those for the rest of the notebook</i></h3>'))

characteristics_dtypes = pd.DataFrame(np.transpose(np.array((characteristics.columns,characteristics.dtypes),dtype=object,)),columns=['features','dtype'])
vehicles_dtypes = pd.DataFrame(np.transpose(np.array((vehicles.columns,vehicles.dtypes),dtype=object,)),columns=['features','dtype'])
places_dtypes = pd.DataFrame(np.transpose(np.array((places.columns,places.dtypes),dtype=object,)),columns=['features','dtype'])
drivers_dtypes = pd.DataFrame(np.transpose(np.array((drivers.columns,drivers.dtypes),dtype=object,)),columns=['features','dtype'])


characteristics_dtypes = characteristics_dtypes.style.set_table_styles([{
    'selector': 'caption',
    'props': [
        ('color', '#585858'),
        ('font-size', '30px')
    ]
}])
vehicles_dtypes = vehicles_dtypes.style.set_table_styles([{
    'selector': 'caption',
    'props': [
        ('color', '#585858'),
        ('font-size', '30px')
    ]
}])
places_dtypes = places_dtypes.style.set_table_styles([{
    'selector': 'caption',
    'props': [
        ('color', '#585858'),
        ('font-size', '30px')
    ]
}])
drivers_dtypes = drivers_dtypes.style.set_table_styles([{
    'selector': 'caption',
    'props': [
        ('color', '#585858'),
        ('font-size', '30px')
    ]
}])


characteristics_dtypes_styler = characteristics_dtypes.set_table_attributes("style='display:inline'").set_caption('characteristics')
vehicles_dtypes_styler = vehicles_dtypes.set_table_attributes("style='display:inline'").set_caption('vehicles')
places_dtypes_styler = places_dtypes.set_table_attributes("style='display:inline'").set_caption('places')
drivers_dtypes_styler = drivers_dtypes.set_table_attributes("style='display:inline'").set_caption('drivers')
space = "\xa0" * 50
display_html(characteristics_dtypes_styler._repr_html_() + space + vehicles_dtypes_styler._repr_html_() + space + 
             places_dtypes_styler._repr_html_() + space + drivers_dtypes_styler._repr_html_(), raw=True)

for col in characteristics.select_dtypes("object"):
    print('\n')
    print('Number of values in "',col,'"', {characteristics[col].nunique()})
    print(characteristics[col].unique())
    print('\n')
    print('------------------------------------------------')


Number of values in " dep " {107}
['93' '92' '94' '87' '69' '38' '34' '13' '988' '976' '974' '972' '2B' '91'
 '86' '83' '80' '78' '77' '76' '72' '71' '67' '66' '64' '60' '51' '50'
 '49' '45' '37' '35' '33' '31' '30' '29' '22' '19' '18' '17' '74' '81' '2'
 '59' '95' '63' '62' '973' '2A' '84' '9' '73' '43' '10' '36' '16' '7' '21'
 '40' '24' '4' '85' '27' '28' '52' '68' '42' '82' '11' '987' '44' '61'
 '14' '56' '58' '54' '47' '41' nan '3' '75' '1' '57' '32' '39' '15' '23'
 '6' '5' '26' '48' '986' '971' '89' '25' '12' '88' '65' '53' '70' '46'
 '90' '8' '79' '977' '55' '978' '975']


------------------------------------------------


Number of values in " com " {11421}
['93053' '93066' '92036' ... '67473' '85099' '76462']


------------------------------------------------


Number of values in " adr " {31934}
['AUTOROUTE A3' 'AUTOROUTE A1' 'AUTOROUTE A86' ... 'Route de Castelnau'
 'Route de Nieul-le-Dolent' "Boulevard l'Alouette"]


------------------------------------------------

sns.set(font_scale = 1.5)
plt.figure(figsize=(10, 30))
plt.title('Number of accidents in 2019 per Department')
sns.countplot(y=characteristics['dep'])
plt.xlabel("Number of accidents")
plt.ylabel("Department")
plt.show()

sns.set(font_scale = 1.5)
fig, ax = plt.subplots(3,4, figsize=(30, 15))
i=0
for col in characteristics.select_dtypes(include=['float64','int64']):
    sns.distplot(characteristics[col],label=col,ax=ax[i//4][i%4])
    i=i+1
fig.show()

for col in vehicles.select_dtypes("object"):
    print('\n')
    print('Number of values in "',col,'"', {vehicles[col].nunique()})
    print(vehicles[col].unique())
    print('\n')
    print('------------------------------------------------')


Number of values in " num_veh " {48}
['B01' 'A01' 'C01' 'Z01' 'D01' 'E01' 'AB01' 'Y01' 'I01' 'T01' 'O01' 'G01'
 'F01' 'PB01' 'FB01' 'M01' 'LB01' 'H01' 'J01' 'K01' 'L01' 'CB01' 'X01'
 'N01' 'W01' 'U01' 'V01' 'MB01' 'RA01' 'TC01' 'R01' 'Q01' 'GB01' 'MA01'
 'VB01' 'RC01' 'BA01' 'TB01' '[01' '\\01' 'VF01' 'ZZ01' 'P01' 'DA01'
 'AA01' 'BB01' 'ZB01' 'BC01']


------------------------------------------------

sns.set(font_scale = 1.5)
plt.figure(figsize=(10, 15))
plt.title('Number of accidents in 2019 per number of occupants (by category)')
sns.countplot(y=vehicles['num_veh'])
plt.xlabel("Number of accidents")
plt.ylabel("Category")
plt.show()

sns.set(font_scale = 1.5)
fig, ax = plt.subplots(3,3, figsize=(30, 10))
i=0
for col in vehicles.select_dtypes(include=['float64','int64']):
    sns.distplot(vehicles[col],label=col,ax=ax[i//3][i%3])
    i=i+1
fig.show()

for col in places.select_dtypes("object"):
    print('\n')
    print('Number of values in "',col,'"', {places[col].nunique()})
    print(places[col].unique())
    print('\n')
    print('------------------------------------------------')


Number of values in " voie " {14327}
['3' '1' '86' ... 'PRESIDENT ROOSEVELT (RUE DU) N°2 A 26' 'VC du Rocher'
 'Gabriel Péri (AV)']


------------------------------------------------


Number of values in " v2 " {35}
[nan 'INT' 'B' 'D' ' -' 'A' 'N' 'R' 'E' 'F' 'C' 'EXT' 'Z' 'I' 'X' 'W' 'Y'
 'b' 'G' 'V' 'U' 'L' 'M' 'H' 'T' 'S' 'P' 'O' '15' 'K' 'II' '1A' 'IV' ' D'
 'A1' 'CD']


------------------------------------------------

sns.set(font_scale = 1.5)
fig, ax = plt.subplots(3,5, figsize=(30, 15))
i=0
for col in places.select_dtypes(include=['float64','int64']):
    sns.distplot(places[col],label=col,ax=ax[i//5][i%5])
    i=i+1
fig.show()

for col in drivers.select_dtypes("object"):
    print('\n')
    print('Number of values in "',col,'"', {drivers[col].nunique()})
    print(drivers[col].unique())
    print('\n')
    print('------------------------------------------------')


Number of values in " num_veh " {29}
['B01' 'A01' 'C01' 'D01' 'E01' 'Z01' 'Y01' 'I01' 'T01' 'O01' 'G01' 'F01'
 'M01' 'LB01' 'H01' 'J01' 'K01' 'L01' 'N01' 'W01' 'X01' 'U01' 'V01' 'Q01'
 'MA01' 'CB01' '\\01' 'VF01' 'P01']


------------------------------------------------


Number of values in " actp " {13}
['-1' '0' '3' '2' '1' 'B' '4' '9' '5' 'A' '8' '6' '7']


------------------------------------------------

sns.set(font_scale = 1.5)
plt.figure(figsize=(10, 5))
plt.title('Number of accidents in 2019 sorted by pedestrian accions')
sns.countplot(y=drivers['actp'])
plt.xlabel("Number of accidents")
plt.ylabel("Category")
plt.show()

sns.set(font_scale = 1.5)
fig, ax = plt.subplots(3,4, figsize=(30, 15))
i=0
for col in drivers.select_dtypes(include=['float64','int64']):
    sns.distplot(drivers[col],label=col,ax=ax[i//4][i%4])
    i=i+1
fig.show()

characteristics = pd.read_csv('../input/2019-database-of-road-traffic-injuries/caracteristiques-2019.csv')
characteristics.name = 'characteristics'
places = pd.read_csv('../input/2019-database-of-road-traffic-injuries/lieux-2019.csv')
places.name = 'places'
drivers = pd.read_csv('../input/2019-database-of-road-traffic-injuries/usagers-2019.csv')
drivers.name = 'drivers'
vehicles = pd.read_csv('../input/2019-database-of-road-traffic-injuries/vehicules-2019.csv')
vehicles.name = 'vehicles'

datasets = [characteristics,places,vehicles,drivers]

# Indexing the tables
characteristics = characteristics.set_index('Num_Acc')
places = places.set_index('Num_Acc')
vehicles = vehicles.set_index('id_vehicule')
drivers = drivers.set_index('id_vehicule')

# Dealing with features with too many NaNs 
vehicles = vehicles.drop('occutc',axis=1)
places = places.drop(['v2','lartpc','larrout'],axis=1)

# Dealing with features according to the EDA
characteristics = characteristics.drop(['an','adr','com'],axis=1)
characteristics['lat']=characteristics['lat']/10000000
characteristics['long']=characteristics['long']/10000000
characteristics = characteristics.drop('201900033874',axis=0)
#characteristics = characteristics[characteristics['dep']!='2B'] # comment / uncomment
#characteristics = characteristics[characteristics['dep']!='2A'] # comment / uncomment
#characteristics = characteristics[(characteristics['dep'].astype(float)<100)] # comment / uncomment
#places = places.loc[characteristics.index.values] # comment / uncomment
places = places.drop('201900033874',axis=0) # comment / uncomment
places = places.drop(['v1','vosp','pr','voie'],axis=1)
vehicles = vehicles.drop('obs',axis=1)
drivers = drivers.drop(['secu3'],axis=1)

pd.set_option('display.max_row',max(characteristics.shape[0],places.shape[0],drivers.shape[0],vehicles.shape[0]))
pd.set_option('display.max_column',max(characteristics.shape[1],places.shape[1],drivers.shape[1],vehicles.shape[1]))

for df in datasets:
    print ("The dataset",df.name,"has",df.shape[0],"rows and",df.shape[1],"columns")

The dataset characteristics has 58840 rows and 15 columns
The dataset places has 58840 rows and 18 columns
The dataset vehicles has 100710 rows and 11 columns
The dataset drivers has 132977 rows and 15 columns

from sklearn.preprocessing import LabelEncoder
def encoding(df):
    label = LabelEncoder()
    for c in df.select_dtypes("object"):
        df[c]=df[c].astype("|S")
        df[c]=label.fit_transform(df[c])
    return df

def imputation(df):
    df = df.fillna(df.median())
    df = df.dropna()
    return df

def preprocessing(df):
    df = encoding(df)
    df = imputation(df) 

    return df

characteristics = preprocessing(characteristics)
vehicles = preprocessing(vehicles)
places = preprocessing(places)
drivers = preprocessing(drivers)

display(HTML('<h1>characteristics</h1>'))
display(characteristics.head())
display(HTML('<h1>vehicles</h1>'))
display(vehicles.head())
display(HTML('<h1>drivers</h1>'))
display(drivers.head())
display(HTML('<h1>places</h1>'))
display(places.head())

lat = characteristics['lat']
lon = characteristics['long']
dep = characteristics['dep']
catr = places['catr'].map({1 : 'Highway',
2 : 'National road',
3 : 'Departmental road',
4 : 'Communal roads',
5 : 'Outside the public network',
6 : 'Parking lot open to public traffic',
7 : 'Urban metropolis roads',
9 : 'other'})
lum = characteristics['lum'].map({1 : 'Full day',
2 : 'Twilight or dawn',
3 : 'Night without public lighting',
4 : 'Night with public lighting not on',
5 : 'Night with public lighting on'})
atm = characteristics['atm'].map({1 : 'Normal',
2 : 'Light rain',
3 : 'Heavy rain',
4 : 'Snow. hail',
5 : 'Fog. smoke',
6 : 'Strong wind. storm',
7 : 'Dazzling weather',
8 : 'Cloudy weather',
9 : 'Other'})
col = characteristics['col'].map({1 : 'Two vehicles. frontal',
2 : 'Two vehicles. from the rear',
3 : 'Two vehicles. from the side',
4 : 'Three vehicles and more. in a chain',
5 : 'Three or more vehicles. multiple collisions',
6 : 'Other collision 7. No collision'})
circ = places['circ'].map({1 : 'One way',
2 : 'Bidirectional',
3 : 'A separate carriageway',
4 : 'With variable assignment channels'})
prof = places['prof'].map({1 : 'Flat',
2 : 'Slope',
3 : 'hilltop',
4 : 'Bottom of coast'})
plan = places['plan'].map({1 : 'rectilinear part',
2 : 'In a curve to the left',
3 : 'In a curve to the right',
4 : 'In "S"'})
surf = places['surf'].map({1 : 'Normal',
2 : 'Wet',
3 : 'Puddles',
4 : 'Flooded',
5 : 'Snowy',
6 : 'Mud',
7 : 'Icy',
8 : 'Fat. oil',
9 : 'Other'})
vma = places['vma']

import plotly.express as px
fig = px.scatter_mapbox(characteristics, 
                        lat="lat", 
                        lon="long", 
                        hover_name=catr, 
                        hover_data={'Light':lum,
                                    'Atmosphere':atm,
                                    'Collision':col,
                                    'Regime':circ,
                                    'Profile':prof,
                                    'Layout':plan,
                                    'Surface':surf,
                                    'Speed':vma,
                                    'long':False,
                                    'lat':False}, 
                        zoom=4.9, 
                        height=800, 
                        width=800)
fig.data[0]['marker'].update(color='red') #green
fig.data[0]['marker'].update(size=3)
fig.update_layout(mapbox_style="open-street-map")
fig.update_layout(margin={"r":0,"t":0,"l":0,"b":0})
fig.show()

df_acc = pd.concat([characteristics, places.reindex(characteristics.index)], axis=1)
df_veh = pd.concat([drivers, vehicles.reindex(drivers.index)], axis=1)
pd.set_option('display.max_row',40)
pd.set_option('display.max_column',40)
display(HTML('<h1>df_acc</h1>'))
display(df_acc.head())
display(HTML('<h1>df_veh</h1>'))
display(df_veh.head())

df_acc = df_acc.loc[:,~df_acc.columns.duplicated()] # Get rid of duplicates
df_veh = df_veh.loc[:,~df_veh.columns.duplicated()]
df_veh.reset_index(drop=True, inplace=True)
df_veh.index = df_veh['Num_Acc'].astype('str')
df_veh = df_veh.drop(['Num_Acc'],axis=1)
df = pd.concat([df_acc.reindex(df_veh.index),df_veh],axis=1)
df = preprocessing(df)

pd.set_option('display.max_row',40)
pd.set_option('display.max_column',40)
display(HTML('<h1>df_acc</h1>'))
display(df_acc.head())
display(HTML('<h1>df_veh</h1>'))
display(df_veh.head())
display(HTML('<h1>Fully concatenated dataset : df</h1>'))
display(df.head())
print('\n')
print("----------------------------------")
display(HTML('<h3>Complete dataset shape :</h3>'))
display(df.shape)
print("----------------------------------")


----------------------------------

(132977, 39)

----------------------------------

plt.figure(figsize=(15,6))
sns.countplot(df['grav'].map({1:'Unharmed',
                                  2:'Killed',
                                  3:'Injured hospitalized',
                                  4:'Slightly injured'
                                }))
plt.plot()

[]

# Class count
count_class_4, count_class_1, count_class_3, count_class_2 = df['grav'].value_counts()

# Divide by class
df_class_1 = df[df['grav'] == 1]
df_class_2 = df[df['grav'] == 2]
df_class_3 = df[df['grav'] == 3]
df_class_4 = df[df['grav'] == 4]

df_class_1_under = df_class_1.sample(count_class_2,random_state=42)
df_class_4_under = df_class_4.sample(count_class_2,random_state=42)
df_class_3_under = df_class_3.sample(count_class_2,random_state=42)
df_under = pd.concat([df_class_1_under, df_class_2, df_class_3_under, df_class_4_under], axis=0)

df_class_2_over = df_class_2.sample(count_class_1, replace=True, random_state=42)
df_class_3_over = df_class_3.sample(count_class_1, replace=True, random_state=42)
df_class_4_over = df_class_4.sample(count_class_1, replace=True, random_state=42)
df_over = pd.concat([df_class_1, df_class_2_over, df_class_3_over, df_class_4_over], axis=0)

fig,axes = plt.subplots(1,2,figsize=(20,6),sharey=True)
sns.countplot(ax=axes[0],x=df_under['grav'].map({1:'Unharmed',
                                  2:'Killed',
                                  3:'Injured hospitalized',
                                  4:'Slightly injured'
                                }))
axes[0].set_title('Random Downsampling')
sns.countplot(ax=axes[1],x=df_over['grav'].map({1:'Unharmed',
                                  2:'Killed',
                                  3:'Injured hospitalized',
                                  4:'Slightly injured'
                                }))
axes[1].set_title('Random Oversampling')
plt.plot()

[]

trainset, testset = train_test_split(df_over, test_size=0.15, random_state=42)
fig, ax = plt.subplots(1,2, figsize=(18, 5))
sns.countplot(x = 'grav' , data = trainset,ax=ax[0],palette="Accent").set_title('TrainSet')
sns.countplot(x = 'grav' , data = testset,ax=ax[1],palette="Accent").set_title('TestSet')

Text(0.5, 1.0, 'TestSet')

X_train = trainset.drop('grav',axis=1)
y_train = trainset['grav']
X_test = testset.drop('grav',axis=1)
y_test = testset['grav']

from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
from sklearn.svm import SVC
from sklearn.neighbors import KNeighborsClassifier
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler, RobustScaler, MinMaxScaler
from sklearn.linear_model import LogisticRegression
from sklearn.decomposition import PCA

preprocessor = make_pipeline(StandardScaler())

PCAPipeline = make_pipeline(preprocessor, PCA(n_components=3,random_state=0))

RandomPipeline = make_pipeline(preprocessor,RandomForestClassifier(random_state=0))
AdaPipeline = make_pipeline(preprocessor,AdaBoostClassifier(random_state=0))
SVMPipeline = make_pipeline(preprocessor,SVC(random_state=0,probability=True))
KNNPipeline = make_pipeline(preprocessor,KNeighborsClassifier())
LRPipeline = make_pipeline(preprocessor,LogisticRegression(solver='sag'))

PCA_df = pd.DataFrame(PCAPipeline.fit_transform(df.drop('grav',axis=1)))
PCA_df = pd.concat([PCA_df.reset_index(), df['grav'].map({1:'Unharmed',
                                  2:'Killed',
                                  3:'Injured hospitalized',
                                  4:'Slightly injured'
                                }).reset_index()], axis=1)
PCA_df = PCA_df.drop(['index','Num_Acc'],axis=1)
PCA_df.head()

figure1 = px.scatter_3d(PCA_df,
        x=0, 
        y=1, 
        z=2, 
        color = 'grav',
                       width=600, height=800)
figure1.update_traces(marker=dict(size=5,
                                  line=dict(width=0.15,
                                        color='black')),
                      selector=dict(mode='markers'))

figure1.show()

dict_of_models = {'KNN': KNNPipeline,
                  'RandomForest': RandomPipeline,
                  'AdaBoost': AdaPipeline,
                  #'SVM': SVMPipeline,
                  'LR': LRPipeline}

def evaluation(model):
    model.fit(X_train, y_train)
    # calculating the predictions
    y_pred = model.predict(X_test)
    print('Accuracy = ', accuracy_score(y_test, y_pred))
    print('-')
    print(confusion_matrix(y_test,y_pred))
    print('-')
    print(classification_report(y_test,y_pred))
    print('-')

for name, model in dict_of_models.items():
    print('---------------------------------')
    print(name)
    evaluation(model)

---------------------------------
KNN
Accuracy =  0.72331660781763
-
[[5366  309 1050 1510]
 [   0 7957    0    0]
 [ 857  528 5863  771]
 [2056  373 1479 4167]]
-
              precision    recall  f1-score   support

           1       0.65      0.65      0.65      8235
           2       0.87      1.00      0.93      7957
           3       0.70      0.73      0.71      8019
           4       0.65      0.52      0.57      8075

    accuracy                           0.72     32286
   macro avg       0.72      0.72      0.72     32286
weighted avg       0.71      0.72      0.72     32286

-
---------------------------------
RandomForest
Accuracy =  0.9063680852381837
-
[[7135   13  412  675]
 [   0 7957    0    0]
 [ 120   17 7676  206]
 [1032   20  528 6495]]
-
              precision    recall  f1-score   support

           1       0.86      0.87      0.86      8235
           2       0.99      1.00      1.00      7957
           3       0.89      0.96      0.92      8019
           4       0.88      0.80      0.84      8075

    accuracy                           0.91     32286
   macro avg       0.91      0.91      0.91     32286
weighted avg       0.91      0.91      0.91     32286

-
---------------------------------
AdaBoost
Accuracy =  0.5417828160812737
-
[[6161  561  487 1026]
 [ 597 4925 1697  738]
 [ 885 2706 2672 1756]
 [2369  798 1174 3734]]
-
              precision    recall  f1-score   support

           1       0.62      0.75      0.68      8235
           2       0.55      0.62      0.58      7957
           3       0.44      0.33      0.38      8019
           4       0.51      0.46      0.49      8075

    accuracy                           0.54     32286
   macro avg       0.53      0.54      0.53     32286
weighted avg       0.53      0.54      0.53     32286

-
---------------------------------
LR
Accuracy =  0.4776373660410085
-
[[5330 1032  646 1227]
 [ 941 4729 1478  809]
 [1372 2774 2055 1818]
 [2492 1094 1182 3307]]
-
              precision    recall  f1-score   support

           1       0.53      0.65      0.58      8235
           2       0.49      0.59      0.54      7957
           3       0.38      0.26      0.31      8019
           4       0.46      0.41      0.43      8075

    accuracy                           0.48     32286
   macro avg       0.47      0.48      0.46     32286
weighted avg       0.47      0.48      0.47     32286

-

from sklearn.model_selection import RandomizedSearchCV
RandomPipeline.get_params().keys()

dict_keys(['memory', 'steps', 'verbose', 'pipeline', 'randomforestclassifier', 'pipeline__memory', 'pipeline__steps', 'pipeline__verbose', 'pipeline__standardscaler', 'pipeline__standardscaler__copy', 'pipeline__standardscaler__with_mean', 'pipeline__standardscaler__with_std', 'randomforestclassifier__bootstrap', 'randomforestclassifier__ccp_alpha', 'randomforestclassifier__class_weight', 'randomforestclassifier__criterion', 'randomforestclassifier__max_depth', 'randomforestclassifier__max_features', 'randomforestclassifier__max_leaf_nodes', 'randomforestclassifier__max_samples', 'randomforestclassifier__min_impurity_decrease', 'randomforestclassifier__min_impurity_split', 'randomforestclassifier__min_samples_leaf', 'randomforestclassifier__min_samples_split', 'randomforestclassifier__min_weight_fraction_leaf', 'randomforestclassifier__n_estimators', 'randomforestclassifier__n_jobs', 'randomforestclassifier__oob_score', 'randomforestclassifier__random_state', 'randomforestclassifier__verbose', 'randomforestclassifier__warm_start'])

hyper_params = {
    'randomforestclassifier__n_estimators':[10,100,150,250,400,600],
    'randomforestclassifier__criterion':['gini','entropy'],
    'randomforestclassifier__min_samples_split':[2,6,12],
    'randomforestclassifier__min_samples_leaf':[1,4,6,10],
    'randomforestclassifier__max_features':['auto','srqt','log2',int,float],
    'randomforestclassifier__verbose':[0,1,2],
    'randomforestclassifier__class_weight':['balanced','balanced_subsample'],
    'randomforestclassifier__n_jobs':[-1],
}

RF_grid = RandomizedSearchCV(RandomPipeline,hyper_params,scoring='accuracy',n_iter=40)
RF_grid.fit(X_train,y_train)

print(RF_grid.best_params_)

{'randomforestclassifier__verbose': 2, 'randomforestclassifier__n_jobs': -1, 'randomforestclassifier__n_estimators': 250, 'randomforestclassifier__min_samples_split': 6, 'randomforestclassifier__min_samples_leaf': 1, 'randomforestclassifier__max_features': 'auto', 'randomforestclassifier__criterion': 'entropy', 'randomforestclassifier__class_weight': 'balanced'}

best_forest = (RF_grid.best_estimator_)
best_forest.fit(X_train,y_train)
# calculating the predictions
y_pred = best_forest.predict(X_test)

N, train_score, test_score = learning_curve(best_forest, X_train, y_train, 
                                           cv=4, scoring='accuracy', 
                                           train_sizes=np.linspace(0.1,1,10))

print('Accuracy = ', accuracy_score(y_test, y_pred))
print('-')
print(confusion_matrix(y_test,y_pred))
print('-')
print(classification_report(y_test,y_pred))
print('-')
    
plt.figure(figsize=(5,5))
plt.plot(N, train_score.mean(axis=1), label='train score')
plt.plot(N, test_score.mean(axis=1), label='validation score')
plt.legend()
plt.title('Accuracy')
plt.show()

Accuracy =  0.9034566065787029
-
[[7159   13  414  649]
 [   0 7957    0    0]
 [ 153   14 7636  216]
 [1071   18  569 6417]]
-
              precision    recall  f1-score   support

           1       0.85      0.87      0.86      8235
           2       0.99      1.00      1.00      7957
           3       0.89      0.95      0.92      8019
           4       0.88      0.79      0.84      8075

    accuracy                           0.90     32286
   macro avg       0.90      0.90      0.90     32286
weighted avg       0.90      0.90      0.90     32286

-

from sklearn.metrics import roc_curve, auc
from sklearn.preprocessing import label_binarize
from sklearn.multiclass import OneVsRestClassifier

# Binarize the output
y_train = label_binarize(y_train, classes=[1, 2, 3, 4])
y_test = label_binarize(y_test, classes=[1, 2, 3, 4])
n_classes = y_train.shape[1]

# Learn to predict each class against the other
classifier = OneVsRestClassifier(best_forest)
#y_score = classifier.fit(X_train, y_train).decision_function(X_test)
y_score = classifier.fit(X_train, y_train).predict_proba(X_test)

# Compute ROC curve and ROC area for each class
fpr = dict()
tpr = dict()
roc_auc = dict()
for i in range(n_classes):
    fpr[i], tpr[i], _ = roc_curve(y_test[:, i], y_score[:, i])
    roc_auc[i] = auc(fpr[i], tpr[i])

# Compute micro-average ROC curve and ROC area
fpr["micro"], tpr["micro"], _ = roc_curve(y_test.ravel(), y_score.ravel())
roc_auc["micro"] = auc(fpr["micro"], tpr["micro"])

# # Plot of a ROC curve for a specific class
# plt.figure()
# plt.plot(fpr[2], tpr[2], label='ROC curve (area = %0.2f)' % roc_auc[2])
# plt.plot([0, 1], [0, 1], 'k--')
# plt.xlim([0.0, 1.0])
# plt.ylim([0.0, 1.05])
# plt.xlabel('False Positive Rate')
# plt.ylabel('True Positive Rate')
# plt.title('Receiver operating characteristic for class 2')
# plt.legend(loc="lower right")
# plt.show()

# Plot ROC curve
plt.figure(figsize=(15,10))
plt.plot(fpr["micro"], tpr["micro"],
         label='micro-average ROC curve (area = {0:0.2f})'
               ''.format(roc_auc["micro"]))
for i in range(n_classes):
    plt.plot(fpr[i], tpr[i], label='ROC curve of class {0} (area = {1:0.2f})'
                                   ''.format(i, roc_auc[i]))

plt.plot([0, 1], [0, 1], 'k--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic to multi-class')
plt.legend(loc="lower right")
plt.show()

[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  37 tasks      | elapsed:   13.0s
[Parallel(n_jobs=-1)]: Done 158 tasks      | elapsed:   55.4s
[Parallel(n_jobs=-1)]: Done 250 out of 250 | elapsed:  1.5min finished
[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  37 tasks      | elapsed:   10.9s
[Parallel(n_jobs=-1)]: Done 158 tasks      | elapsed:   45.8s
[Parallel(n_jobs=-1)]: Done 250 out of 250 | elapsed:  1.2min finished
[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  37 tasks      | elapsed:   13.7s
[Parallel(n_jobs=-1)]: Done 158 tasks      | elapsed:   59.4s
[Parallel(n_jobs=-1)]: Done 250 out of 250 | elapsed:  1.6min finished
[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done  37 tasks      | elapsed:   14.3s
[Parallel(n_jobs=-1)]: Done 158 tasks      | elapsed:  1.0min
[Parallel(n_jobs=-1)]: Done 250 out of 250 | elapsed:  1.6min finished
[Parallel(n_jobs=2)]: Using backend ThreadingBackend with 2 concurrent workers.
[Parallel(n_jobs=2)]: Done  37 tasks      | elapsed:    0.2s
[Parallel(n_jobs=2)]: Done 158 tasks      | elapsed:    1.3s
[Parallel(n_jobs=2)]: Done 250 out of 250 | elapsed:    2.0s finished
[Parallel(n_jobs=2)]: Using backend ThreadingBackend with 2 concurrent workers.
[Parallel(n_jobs=2)]: Done  37 tasks      | elapsed:    0.2s
[Parallel(n_jobs=2)]: Done 158 tasks      | elapsed:    0.7s
[Parallel(n_jobs=2)]: Done 250 out of 250 | elapsed:    1.1s finished
[Parallel(n_jobs=2)]: Using backend ThreadingBackend with 2 concurrent workers.
[Parallel(n_jobs=2)]: Done  37 tasks      | elapsed:    0.2s
[Parallel(n_jobs=2)]: Done 158 tasks      | elapsed:    0.9s
[Parallel(n_jobs=2)]: Done 250 out of 250 | elapsed:    1.5s finished
[Parallel(n_jobs=2)]: Using backend ThreadingBackend with 2 concurrent workers.
[Parallel(n_jobs=2)]: Done  37 tasks      | elapsed:    0.2s
[Parallel(n_jobs=2)]: Done 158 tasks      | elapsed:    1.0s
[Parallel(n_jobs=2)]: Done 250 out of 250 | elapsed:    1.6s finished

	jour	mois	an	hrmn	lum	dep	com	agg	int	atm	col	adr	lat	long
Num_Acc
201900000001	30.0	11.0	2019.0	0.062500	4.0	93	93053	1.0	1.0	1.0	2.0	AUTOROUTE A3	488962100.0	24701200.0
201900000002	30.0	11.0	2019.0	0.118056	3.0	93	93066	1.0	1.0	1.0	6.0	AUTOROUTE A1	489307000.0	23688000.0
201900000003	28.0	11.0	2019.0	0.635417	1.0	92	92036	1.0	1.0	1.0	4.0	AUTOROUTE A86	489358718.0	23191744.0
201900000004	30.0	11.0	2019.0	0.847222	5.0	94	94069	1.0	1.0	1.0	4.0	A4	488173295.0	24281502.0
201900000005	30.0	11.0	2019.0	0.166667	3.0	94	94028	1.0	1.0	1.0	2.0	A86 INT	487763620.0	24332540.0

	features	missing_rate
0	jour	0.220000
1	mois	0.220000
2	an	0.220000
3	hrmn	0.220000
4	lum	0.220000
5	dep	0.220000
6	com	0.220000
7	agg	0.220000
8	int	0.220000
9	atm	0.220000
10	col	0.220000
11	adr	0.940000
12	lat	0.220000
13	long	0.220000

	features	missing_rate
0	Num_Acc	0.000000
1	num_veh	0.000000
2	senc	0.000000
3	catv	0.000000
4	obs	0.000000
5	obsm	0.000000
6	choc	0.000000
7	manv	0.000000
8	motor	0.000000
9	occutc	99.110000

	features	missing_rate
0	Num_Acc	0.000000
1	num_veh	0.000000
2	place	0.000000
3	catu	0.000000
4	grav	0.000000
5	sexe	0.000000
6	an_nais	0.000000
7	trajet	0.000000
8	secu1	0.000000
9	secu2	0.000000
10	secu3	0.000000
11	locp	0.000000
12	actp	0.000000
13	etatp	0.000000

	jour	mois	hrmn	lum	dep	agg	int	atm	col	lat	long
Num_Acc
201900000001	30.0	11.0	0.062500	4.0	93	1.0	1.0	1.0	2.0	48.896210	2.470120
201900000002	30.0	11.0	0.118056	3.0	93	1.0	1.0	1.0	6.0	48.930700	2.368800
201900000003	28.0	11.0	0.635417	1.0	92	1.0	1.0	1.0	4.0	48.935872	2.319174
201900000004	30.0	11.0	0.847222	5.0	94	1.0	1.0	1.0	4.0	48.817329	2.428150
201900000005	30.0	11.0	0.166667	3.0	94	1.0	1.0	1.0	2.0	48.776362	2.433254

	Num_Acc	num_veh	senc	catv	obs	obsm	choc	manv	motor	occutc
id_vehicule
138 306 524	201900000001	B01	2	7	0	2	5	23	1	NaN
138 306 525	201900000001	A01	2	17	1	0	3	11	1	NaN
138 306 523	201900000002	A01	1	7	4	0	1	0	1	NaN
138 306 520	201900000003	A01	1	7	0	2	1	2	1	NaN
138 306 521	201900000003	B01	1	7	1	0	4	2	1	NaN

	catr	voie	v1	v2	circ	nbv	vosp	prof	pr	pr1	plan	lartpc	larrout	surf	infra	situ	vma
Num_Acc
201900000001	1.0	3	0.0	NaN	3.0	10.0	0.0	1.0	6.0	900.0	2.0	NaN	NaN	1.0	2.0	1.0	70.0
201900000002	1.0	1	0.0	NaN	1.0	2.0	0.0	4.0	3.0	845.0	2.0	NaN	NaN	1.0	0.0	1.0	70.0
201900000003	1.0	86	0.0	NaN	3.0	8.0	0.0	1.0	10.0	500.0	3.0	NaN	NaN	1.0	0.0	1.0	90.0
201900000004	1.0	4	0.0	NaN	3.0	5.0	0.0	1.0	2.0	299.0	1.0	NaN	NaN	1.0	0.0	1.0	90.0
201900000005	1.0	86	0.0	INT	1.0	3.0	0.0	1.0	41.0	0.0	3.0	NaN	NaN	1.0	2.0	1.0	90.0

	features	missing_rate
0	catr	0.040000
1	voie	5.030000
2	v1	18.310000
3	v2	92.920000
4	circ	5.390000
5	nbv	1.150000
6	vosp	1.180000
7	prof	0.070000
8	pr	12.450000
9	pr1	12.960000
10	plan	0.060000
11	lartpc	99.640000
12	larrout	99.370000
13	surf	0.080000
14	infra	0.120000
15	situ	0.240000
16	vma	1.540000

	features	dtype
0	jour	float64
1	mois	float64
2	an	float64
3	hrmn	float64
4	lum	float64
5	dep	object
6	com	object
7	agg	float64
8	int	float64
9	atm	float64
10	col	float64
11	adr	object
12	lat	float64
13	long	float64

	features	dtype
0	Num_Acc	int64
1	num_veh	object
2	senc	int64
3	catv	int64
4	obs	int64
5	obsm	int64
6	choc	int64
7	manv	int64
8	motor	int64
9	occutc	float64

	num_veh	place	catu	grav	sexe	an_nais	trajet	secu1	secu2	locp	actp	etatp	senc	catv	obsm	choc	manv	motor
Num_Acc
201900000001	1	2	2	4	2	2002	0	1	0	-1	0	-1	2	7	2	5	23	1
201900000001	1	1	1	4	2	1993	5	1	0	-1	0	-1	2	7	2	5	23	1
201900000001	0	1	1	1	1	1959	0	1	0	-1	0	-1	2	17	0	3	11	1
201900000002	0	1	1	4	2	1994	0	1	0	-1	0	-1	1	7	0	1	0	1
201900000003	0	1	1	1	1	1996	0	1	0	-1	1	-1	1	7	2	1	2	1

	0	1	2	grav
0	-2.026957	3.645923	-2.153101	Slightly injured
1	-2.769672	3.458293	-1.775232	Slightly injured
2	-2.743502	3.446155	-1.023593	Unharmed
3	-1.418706	2.277790	2.955279	Slightly injured
4	-2.403853	3.466685	-1.137749	Unharmed

Breaking down EDA for a set of 4 datasets¶

characteristics

vehicles

drivers

places

Expand this to read the features description

Num_Acc¶

jour¶

mois¶

an¶

hrmn¶

lum¶

dep¶

com¶

agg¶

int¶

atm¶

col¶

adr¶

lat¶

Long¶

catr¶

voie¶

V1¶

V2¶

circ¶

nbv¶

vosp¶

prof¶

pr¶

pr1¶

plan¶

lartpc¶

larrout¶

surf¶

infra¶

situ¶

vma¶

vehicle_id¶

Num_Veh¶

senc¶

catv¶

obs¶

obsm¶

choc¶

manv¶

motor¶

occutc¶

id_vehicule¶

Num_Veh¶

place¶

catu¶

grav¶

sexe¶

An_nais¶

trajet¶

secu1¶

secu2¶

secu3¶

locp¶

actp¶

etatp¶

Missing values of the different tables (%)

The values highlighted are the ones above a certain threshold of missing values

We will get rid of those for the rest of the notebook

Visualizing datasets dtypes 1 by 1

characteristics

Comments

vehicles

Comments

places

Comments

drivers

Comments

Summary¶

characteristics¶

vehicles¶

places¶

drivers¶

Cleaning data¶